© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13290
    Prev
    Next
    INDEX
    Explanations

    a combination of words related to intimacy, time of day, and HTML

    oai_token-act-pair · gemini-2.0-flash

    Web data/scraped text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.57
    stateMutability
    -0.56
    IndentedString
    -0.55
    HttpPut
    -0.54
    ########.
    -0.54
    )}
    -0.52
    "},
    -0.51
     Gid
    -0.50
    )}</
    -0.50
    '},
    -0.49
    POSITIVE LOGITS
    SharedDtor
    0.56
    FormTagHelper
    0.56
     imprimée
    0.54
    
    0.54
    ▼
    0.52
    coration
    0.52
    CloseOperation
    0.52
     marquées
    0.51
     tourisme
    0.50
    oubliez
    0.50
    Activations Density 9.787%

    No Known Activations